Paper 3 – May/Nov 2018


About paper 3

The paper is normally written on the same day as paper 2 and has a duration of 1 hour, with a maximum mark of 30, counting for 20% of the total subject grade. Every year, it is a based on a case study or scenario that changes.
Here is the case study for the May/November 2018 exams.
The topic is Self Driving Cars and Machine Learning

How to study paper 3: http://ib.compscihub.net/paper3
autonomous driving: IB material

Please download our lesson materials to your own computer!
http://pan.rdfz.cn:80/#/link/67792FE072EEF80505C04AD8440C69CF 有效期限截止:2017-12-16

Class assignment: Overview/ Survey of AI as a whole picture 20171122

Our paper 3 course are going to be in 4 stages:

Stage 1: study MIT course

Learn MIT 6.S094- Deep Learning and Self-Driving Cars Course!
Course website: https://selfdrivingcars.mit.edu/ ,all slides are videos can be downloaded from this page
There are 5 lectures, each about 90 minutes.

Lecture 1: learning summary deadline 20171120
Lecture 2: learning summary deadline 20171206
Lecture 3: learning summary
Lecture 4: learning summary
Lecture 5: learning summary

Stage 2: practical hands-on projects

During course learning, you will do the following 2 projects:
Deep Traffic:
Tutorial: https://selfdrivingcars.mit.edu/deeptraffic/
project page: https://selfdrivingcars.mit.edu/deeptrafficjs/ create and evaluate your own NN
DeepTraffic: learning summary + project submission

DeepTesla:
Tutorial: https://selfdrivingcars.mit.edu/deeptesla/
project page: https://selfdrivingcars.mit.edu/deepteslajs/
DeepTesla: learning summary + project submission

Stage 3: Baidu apollo auto driving platform

We are going to simulate our own self driving cars in baidu open source platform.
You are going to have a contest for auto drive!
http://apollo.auto/index_cn.html
http://apollo.auto/developer_cn.html
http://mp.weixin.qq.com/s/9pdQU1L0CJwu_pjEIIg--Q
https://m.sohu.com/a/202555419_355140/?pvid=000115_3w_a

Stage 4: summarize all the key points in the case study material

To formulate your own case study booklet + webpage
Then we are going to review all materials to develop an online high school self driving course by ourselves.


https://computersciencewiki.org/index.php/Template_for_student-defined_terms Template for students defined terms

challenges faced:

  • understand the basic functioning of CNNs as outlined in the case study (Tom)

  • analyse and test the nearest-neighbour and Dijkstra’s algorithms that have been considered for the bus and taxi projects (Arthur)

  • be able to respond to the social and ethical challenges to their project (Charles)

  • incorporate appropriate technology throughout the town that would support their autonomous vehicles project. (Alex)


social issues:


  • the “Trolley Problem”
  • the use of neural networks that produce solutions that we don’t really understand (Michael)

  • the beta-testing of autonomous car systems on public roads. (Doris)

  • understand the basic theory involved in the functioning of the path-fnding algorithms being employed. (Enzo)



  1. Autonomous (Doris)
  2. Backpropagation (Tom)
  3. BigO notation (Doris)
  4. Bounding boxes (Doris)
  5. Brute-force (Enzo)
  6. Convolutional neural networks (CNNs) (Tom)
  7. Cost function (Arthur)
  8. Deep learning (Tom)
  9. Dijkstra’s algorithm (Enzo)
  10. End-to-end learning (Tom)
  11. Feature maps (Activation maps) (Alex)
  12. Filters (Kernels) (Alex)
  13. Filter stride (Alex)
  14. Greedy algorithm (Arthur)
  15. Machine learning (Michael)
  16. Max-pooling / Pooling (Charles)
  17. Multi-layer perceptron (MLP) (Arthur)
  18. Nearest neighbour algorithm (Arthur)
  19. Overfitting (Charles)
  20. Point clouds (Doris)
  21. Receptive field (Alex)
  22. Sensor Fusion (Charles)
  23. Society of Automotive Engineers (Enzo)
  24. Shift invariance (Spatial invariance) (Michael)
  25. Vehicle-to-vehicle (VTV) protocol (Michael)
  26. Vehicle-to-infrastructure (VTI) protocol (Michael)